{"id":6688,"date":"2021-08-21T01:54:41","date_gmt":"2021-08-20T16:54:41","guid":{"rendered":"https:\/\/wp.study3.biz\/?p=6688"},"modified":"2021-08-21T01:55:46","modified_gmt":"2021-08-20T16:55:46","slug":"amd-ryzen-threadripper-pro-3995wx-64-cores-windows10-pro-rtx2080ti-cuda-11-3-250%e5%84%84%e6%a1%81-%e5%86%86%e5%91%a8%e7%8e%87-pi-benchmark%e3%82%92%e5%8b%95%e4%bd%9c%e3%81%95%e3%81%9b%e3%81%a6","status":"publish","type":"post","link":"https:\/\/wp.study3.biz\/?p=6688","title":{"rendered":"AMD Ryzen Threadripper PRO 3995WX 64-Cores Windows10 Pro RTX2080Ti CUDA 11.3 250\u5104\u6841 \u5186\u5468\u7387 Pi Benchmark\u3092\u52d5\u4f5c\u3055\u305b\u3066\u307f\u305f 359.677 seconds ( 5.995 minutes )\u3000"},"content":{"rendered":"

\"\"
\ny-cruncher v0.7.8 Build 9507 ( www.numberworld.org )
\nCopyright 2008-2020 Alexander J. Yee ( a-yee@u.northwestern.edu )<\/p>\n

Distribute Freely – Please report any bugs.<\/p>\n

Tuning: Windows\/19-ZN2 ~ Kagari – Zen 2 Matisse (x64 ADX)<\/p>\n

0 Benchmark Pi (all in ram)
\n 1 Component Stress Tester
\n 2 Run I\/O Performance Analysis<\/p>\n

3 Custom Compute a Constant
\n – Compute other constants (e, Golden Ratio, etc…)
\n – Choose your own settings (use disk for large computations)<\/p>\n

4 BBP Digit Extractor for Pi
\n 5 Digit Viewer<\/p>\n

6 Advanced Options
\n 7 About<\/p>\n

Enter your choice:
\noption: 0<\/p>\n

Benchmark Pi:<\/p>\n

Select a Benchmark Type:<\/p>\n

0 Single-Threaded
\n 1 Multi-Threaded<\/p>\n

option: 1<\/p>\n

Available Memory: 123 GiB<\/p>\n

Option Decimal Digits Approx. Memory Needed<\/p>\n

1 25,000,000 2.96 GiB
\n 2 50,000,000 2.99 GiB
\n 3 100,000,000 3.13 GiB
\n 4 250,000,000 3.52 GiB
\n 5 500,000,000 4.25 GiB
\n 6 1,000,000,000 5.91 GiB
\n 7 2,500,000,000 12.5 GiB
\n 8 5,000,000,000 23.5 GiB
\n 9 10,000,000,000 46.0 GiB
\n 10 25,000,000,000 116 GiB
\n 11 50,000,000,000 230 GiB
\n 12 100,000,000,000 459 GiB
\n 13 250,000,000,000 1.12 TiB
\n 14 500,000,000,000 2.24 TiB
\n 15 1,000,000,000,000 4.49 TiB
\n 16 2,500,000,000,000 11.3 TiB<\/p>\n

0 I prefer SuperPi sizes… (1M, 2M, 4M…)<\/p>\n

option: 10<\/p>\n

Unable to acquire the permission, “SeLockMemoryPrivilege”.
\nLarge pages and page locking may not be possible.<\/p>\n

Expect larger performance penalties from Meltdown mitigation.<\/p>\n

Constant: Pi
\nAlgorithm: Chudnovsky (1988)<\/p>\n

Decimal Digits: 25,000,000,000
\nHexadecimal Digits: Disabled<\/p>\n

Computation Mode: Ram Only
\nMulti-Threading: Cilk Plus Work-Stealing -> 128 \/ 128<\/p>\n

Start Time: Mon Apr 26 12:37:17 2021<\/p>\n

Working Memory… 116 GiB (locked, spread: 100%\/1)
\nTwiddle Tables… 292 MiB (locked, spread: 100%\/1)<\/p>\n

Begin Computation:<\/p>\n

Series CommonP2B3… 1,762,841,746 terms (Expansion Factor = 2.995)
\nTime: 331.075 seconds ( 5.518 minutes )
\nLarge Division…
\n Iterating: 0 O1M ( 6,250,000,0 Time: 13.736 seconds ( 0.229 minutes )
\nInvSqrt(10005)…
\n Time: 9.187 seconds ( 0.153 minutes )
\nLarge Multiply…
\n Time: 5.669 seconds ( 0.094 minutes )<\/p>\n

Pi: 359.677 seconds ( 5.995 minutes )<\/strong><\/p>\n

Base Converting:
\n Time: 24.305 seconds ( 0.405 minutes )
\nWriting Decimal Digits:
\n Time: 3.929 seconds ( 0.065 minutes )<\/p>\n

Start Time: Mon Apr 26 12:37:17 2021
\nEnd Time: Mon Apr 26 12:44:57 2021<\/p>\n

Total Computation Time: 383.986 seconds ( 6.400 minutes )
\nStart-to-End Wall Time: 459.478 seconds ( 7.658 minutes )<\/p>\n

CPU Utilization: 11652.90 % + 192.05 % kernel overhead
\nMulti-core Efficiency: 91.04 % + 1.50 % kernel overhead<\/p>\n

Last Decimal Digits: Pi
\n2448547079 5329693979 7145627081 9204187454 9483487803 : 24,999,999,950
\n1309759846 5364560010 7388984278 8403481193 9913806533 : 25,000,000,000<\/p>\n

Spot Check: Good through 25,000,000,000<\/p>\n

Version: 0.7.8.9507 (Windows\/19-ZN2 ~ Kagari)
\nProcessor(s): AMD Ryzen Threadripper PRO 3995WX 64-Cores
\nTopology: 128 threads \/ 64 cores \/ 1 socket \/ 2 NUMA nodes
\nPhysical Memory: 137,438,953,472 ( 128 GiB)
\nCPU Base Frequency: 2,694,965,472 Hz
\n\u53c2\u8003\u30b5\u30a4\u30c8<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

y-cruncher v0.7.8 Build 9507 ( www.numberworld.org ) Copyright 2008-2020 Alexander J. Yee ( a-yee@u.northweste … \u7d9a\u304d\u3092\u8aad\u3080 →<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[18,10],"tags":[],"class_list":["post-6688","post","type-post","status-publish","format-standard","hentry","category-nvidia","category-windows"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts\/6688","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6688"}],"version-history":[{"count":4,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts\/6688\/revisions"}],"predecessor-version":[{"id":6695,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=\/wp\/v2\/posts\/6688\/revisions\/6695"}],"wp:attachment":[{"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6688"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6688"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.study3.biz\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6688"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}